摘要
针对传统的零件质量测量手段操作复杂、效率低等问题,该文提出基于大像幅非量测数码相机的单目视觉检测方法。首先基于二维直接线性变换和光束法平差进行相机内参数的标定;其次基于平面控制点信息进行单幅影像外方位元素的解算;然后进行影像的畸变纠正和垂直纠正;最后基于轮廓线的多特征提取方法求解零件特征参数等。将大像幅非量测数码相机用于较大平面薄片类零件检测的结果与三坐标量测仪的检测数据对比,实验结果表明,其量测误差小于0.1mm,满足较大幅平面薄片类零件尺寸量测的要求。
In this paper, a monocular visual inspection method based on the large relative amplitude non-metric digital camera for larger flat sheet parts was designed. The research contents include camera parameter calibration based on two-dimensional DLT and bundle adjustment, a single image exterior orientation elements solver based on the information of planar control point, the method of image distortion corrected and vertical corrective, and the part contour features obtained method based on multi-feature extraction method. The detection results of the large amplitude non-measurement digital camera for larger flat sheet parts was compared with the standard data. Experimental results showed that the measurement error was less than 0. 1 mm, which could meet the measurement accuracy requirement of substantially size flat sheet parts.
出处
《测绘科学》
CSCD
北大核心
2017年第2期172-176,182,共6页
Science of Surveying and Mapping
基金
国家自然科学基金项目(41301518)
山东省高等学校科技计划项目(J15LN32)
山东省自然科学基金项目(ZR2014DL001)
山东理工大学博士科研基金项目(413050
413042)
关键词
视觉测量
非量测数码相机
平面薄片零件
影像纠正
visual inspection
non-metric digital camera
flat sheet parts
image correction
